AIConfPaper
← All conferences

ICLR 2025 Accepted Papers

The full list of 3,704 papers accepted at ICLR 2025 (International Conference on Learning Representations). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Poster: 3,111Spotlight: 380Oral: 213
  1. UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic SegmentationPoster1 citations
  2. URLOST: Unsupervised Representation Learning without Stationarity or TopologyPoster1 citations
  3. Ultra-Sparse Memory NetworkPoster1 citations
  4. Uncertainty Modeling in Graph Neural Networks via Stochastic Differential EquationsSpotlight1 citations
  5. Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human FeedbackPoster1 citations
  6. Understanding Constraint Inference in Safety-Critical Inverse Reinforcement LearningPoster1 citations
  7. Understanding Optimization in Deep Learning with Central FlowsPoster1 citations
  8. Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D DetectionPoster1 citations
  9. UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSPPoster1 citations
  10. UniCoTT: A Unified Framework for Structural Chain-of-Thought DistillationPoster1 citations
  11. UniDetox: Universal Detoxification of Large Language Models via Dataset DistillationPoster1 citations
  12. UniDrive: Towards Universal Driving Perception Across Camera ConfigurationsPoster1 citations
  13. Universal Image Restoration Pre-training via Degradation ClassificationPoster1 citations
  14. Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model AccuracyPoster1 citations
  15. Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign RelearningPoster1 citations
  16. Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute AlignmentPoster1 citations
  17. Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-TuningPoster1 citations
  18. Unlocking Point Processes through Point Set DiffusionPoster1 citations
  19. Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction TuningOral1 citations
  20. Unsupervised Meta-Learning via In-Context LearningPoster1 citations
  21. Unsupervised Model Tree Heritage RecoveryPoster1 citations
  22. Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and AmendmentPoster1 citations
  23. VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in MeteorologyPoster1 citations
  24. VEDIT: Latent Prediction Architecture For Procedural Video Representation LearningPoster1 citations
  25. VL-ICL Bench: The Devil in the Details of Multimodal In-Context LearningPoster1 citations
  26. Varying Shades of Wrong: Aligning LLMs with Wrong Answers OnlyPoster1 citations
  27. VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?Poster1 citations
  28. Walk the Talk? Measuring the Faithfulness of Large Language Model ExplanationsSpotlight1 citations
  29. Wasserstein Distances, Neuronal Entanglement, and SparsitySpotlight1 citations
  30. What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary TraitsPoster1 citations
  31. What to align in multimodal contrastive learning?Poster1 citations
  32. What's the Move? Hybrid Imitation Learning via Salient PointsPoster1 citations
  33. When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI InteractionPoster1 citations
  34. When do GFlowNets learn the right distribution?Spotlight1 citations
  35. X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving ScenariosPoster1 citations
  36. X-Fi: A Modality-Invariant Foundation Model for Multimodal Human SensingPoster1 citations
  37. ZAPBench: A Benchmark for Whole-Brain Activity Prediction in ZebrafishSpotlight1 citations
  38. ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot LearningPoster1 citations
  39. Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward InferencePoster1 citations
  40. cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EMPoster1 citations
  41. dEBORA: Efficient Bilevel Optimization-based low-Rank AdaptationPoster1 citations
  42. eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum ChannelsPoster1 citations
  43. $F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from VideosPoster
  44. $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity GraphsPoster
  45. $\phi$-Update: A Class of Policy Update Methods with Policy Convergence GuaranteePoster
  46. $\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial ExamplesPoster
  47. $\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language ModelsPoster
  48. $\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution MapsPoster
  49. $q$-exponential family for policy optimizationPoster
  50. 3D StreetUnveiler with Semantic-aware 2DGS - a simple baselinePoster
  51. 3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text ModelingPoster
  52. 3D-SPATIAL MULTIMODAL MEMORYPoster
  53. 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D EditingPoster
  54. 3DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance GenerationSpotlight
  55. 3DMolFormer: A Dual-channel Framework for Structure-based Drug DiscoveryPoster
  56. A CLIP-Powered Framework for Robust and Generalizable Data SelectionSpotlight
  57. A Causal Lens for Learning Long-term Fair PoliciesPoster
  58. A Computational Framework for Modeling Emergence of Color Vision in the Human BrainOral
  59. A Deep Generative Learning Approach for Two-stage Adaptive Robust OptimizationPoster
  60. A Differentiable Rank-Based Objective for Better Feature LearningPoster
  61. A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline DemonstrationsPoster
  62. A General Framework for Off-Policy Learning with Partially-Observed RewardPoster
  63. A Generalist Hanabi AgentPoster
  64. A Generic Framework for Conformal FairnessPoster
  65. A Graph Enhanced Symbolic Discovery Framework For Efficient Logic OptimizationPoster
  66. A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow GenerationPoster
  67. A Large-scale Training Paradigm for Graph Generative ModelsPoster
  68. A Meta-Learning Approach to Bayesian Causal DiscoveryPoster
  69. A Multi-Power Law for Loss Curve Prediction Across Learning Rate SchedulesPoster
  70. A Multiscale Frequency Domain Causal Framework for Enhanced Pathological AnalysisPoster
  71. A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile GenerationPoster
  72. A Riemannian Framework for Learning Reduced-order Lagrangian DynamicsPoster
  73. A Robust Method to Discover Causal or Anticausal RelationPoster
  74. A Simple Framework for Open-Vocabulary Zero-Shot SegmentationPoster
  75. A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal DiscoveryPoster
  76. A Solvable Attention for Neural Scaling LawsPoster
  77. A Statistical Approach for Controlled Training Data DetectionPoster
  78. A Stochastic Approach to the Subset Selection Problem via Mirror DescentPoster
  79. A Theoretical Analysis of Self-Supervised Learning for Vision TransformersPoster
  80. A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training LoopsPoster
  81. A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of MoleculesOral
  82. A Theory of Initialisation's Impact on SpecialisationPoster
  83. A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization ProblemsPoster
  84. A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned AttentionPoster
  85. A Truncated Newton Method for Optimal TransportPoster
  86. A deep inverse-mapping model for a flapping robotic wingPoster
  87. A transfer learning framework for weak to strong generalizationPoster
  88. A3D: Does Diffusion Dream about 3D Alignment?Poster
  89. ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM CollaborationPoster
  90. ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-EnsemblePoster
  91. ADAM Optimization with Adaptive Batch SelectionPoster
  92. ADAPT: Attentive Self-Distillation and Dual-Decoder Prediction Fusion for Continual Panoptic SegmentationPoster
  93. ADMM for Nonconvex Optimization under Minimal Continuity AssumptionPoster
  94. ADMM for Structured Fractional MinimizationPoster
  95. ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuningPoster
  96. AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing AttacksPoster
  97. AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate StatementsPoster
  98. AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk CategoriesSpotlight
  99. ALBAR: Adversarial Learning approach to mitigate Biases in Action RecognitionPoster
  100. ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learningPoster
  101. APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel EncodingPoster
  102. ASTrA: Adversarial Self-supervised Training with Adaptive-AttacksPoster
  103. Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad GeneralizationPoster
  104. Accelerated training through iterative gradient propagation along the residual pathOral
  105. Accelerating 3D Molecule Generation via Jointly Geometric Optimal TransportPoster
  106. Accelerating Diffusion Transformers with Token-wise Feature CachingPoster
  107. Accelerating Goal-Conditioned Reinforcement Learning Algorithms and ResearchSpotlight
  108. Accelerating Neural ODEs: A Variational Formulation-based ApproachPoster
  109. Accelerating Task Generalisation with Multi-Level Skill HierarchiesPoster
  110. Accelerating neural network training: An analysis of the AlgoPerf competitionPoster
  111. Action Sequence Augmentation for Action AnticipationPoster
  112. Action abstractions for amortized samplingPoster
  113. Active Learning for Continual Learning: Keeping the Past Alive in the PresentPoster
  114. Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise AdaptivitySpotlight
  115. Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data SelectionPoster
  116. Adaptive Batch Size for Privately Finding Second-Order Stationary PointsSpotlight
  117. Adaptive Camera Sensor for Vision ModelsPoster
  118. Adaptive Energy Alignment for Accelerating Test-Time AdaptationPoster
  119. Adaptive Gradient Clipping for Robust Federated LearningSpotlight
  120. Adaptive Pruning of Pretrained Transformer via Differential InclusionsPoster
  121. Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA AdaptersPoster
  122. Adaptive Retention & Correction: Test-Time Training for Continual LearningPoster
  123. Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain TrajectoriesPoster
  124. Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in TransformersPoster
  125. Adaptive backtracking line searchPoster
  126. Addressing Label Shift in Distributed Learning via Entropy RegularizationPoster
  127. AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention DisruptionPoster
  128. Advancing Graph Generation through Beta DiffusionPoster
  129. Advancing Out-of-Distribution Detection via Local NeuroplasticityPoster
  130. Advantage Alignment AlgorithmsOral
  131. Advantage-Guided Distillation for Preference Alignment in Small Language ModelsSpotlight
  132. Adversarial Generative Flow Network for Solving Vehicle Routing ProblemsPoster
  133. Adversarial Latent Feature Augmentation for FairnessPoster
  134. Adversarial Mixup UnlearningPoster
  135. Adversarial Policy Optimization for Offline Preference-based Reinforcement LearningPoster
  136. Adversarial Training for Defense Against Label Poisoning AttacksPoster
  137. Adversarially Robust Anomaly Detection through Spurious Negative Pair MitigationPoster
  138. Adversaries With Incentives: A Strategic Alternative to Adversarial RobustnessPoster
  139. Affine Steerable Equivariant Layer for Canonicalization of Neural NetworksPoster
  140. Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional EquivalencePoster
  141. Alchemy: Amplifying Theorem-Proving Capability Through Symbolic MutationPoster
  142. Algorithmic Stability Based Generalization Bounds for Adversarial TrainingPoster
  143. Aligned Datasets Improve Detection of Latent Diffusion-Generated ImagesPoster
  144. Aligned LLMs Are Not Aligned Browser AgentsPoster
  145. Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual PerceptionPoster
  146. An Asynchronous Bundle Method for Distributed Learning ProblemsPoster
  147. An Auditing Test to Detect Behavioral Shift in Language ModelsPoster
  148. An Effective Manifold-based Optimization Method for Distributionally Robust ClassificationPoster
  149. An Effective Theory of Bias AmplificationPoster
  150. An Efficient Framework for Crediting Data Contributors of Diffusion ModelsPoster
  151. An Exploration with Entropy Constrained 3D Gaussians for 2D Video CompressionPoster
  152. An Optimal Discriminator Weighted Imitation Perspective for Reinforcement LearningPoster
  153. Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search MethodsPoster
  154. Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data SpectraSpotlight
  155. Animate Your Thoughts: Reconstruction of Dynamic Natural Vision from Human Brain ActivityPoster
  156. AnoLLM: Large Language Models for Tabular Anomaly DetectionPoster
  157. Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice QuestionsSpotlight
  158. Anti-Exposure Bias in Diffusion ModelsSpotlight
  159. Anyprefer: An Agentic Framework for Preference Data SynthesisPoster
  160. Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton InfluencePoster
  161. Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?Poster
  162. Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music ModelingPoster
  163. AstroCompress: A benchmark dataset for multi-purpose compression of astronomical dataPoster
  164. Asymmetric Factorized Bilinear Operation for Vision TransformerPoster
  165. Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with StructurePoster
  166. Attribute-based Visual Reprogramming for Vision-Language ModelsPoster
  167. AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-ResolutionPoster
  168. Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented GenerationPoster
  169. AutoBencher: Towards Declarative Benchmark ConstructionPoster
  170. AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled DemonstrationsSpotlight
  171. AutoG: Towards automatic graph construction from tabular dataPoster
  172. AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly DetectionPoster
  173. Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space ModelsPoster
  174. Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning TasksPoster
  175. BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward ShapingPoster
  176. BANGS: Game-theoretic Node Selection for Graph Self-TrainingPoster
  177. BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as ExpertsPoster
  178. BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RLPoster
  179. BP-Modified Local Loss for Efficient Training of Deep Neural NetworksPoster
  180. BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral DataPoster
  181. BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIPPoster
  182. BadRobot: Jailbreaking Embodied LLM Agents in the Physical WorldPoster
  183. Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximationsPoster
  184. Balanced Ranking with Relative Centrality: A multi-core periphery perspectivePoster
  185. Balancing Act: Diversity and Consistency in Large Language Model EnsemblesPoster
  186. Balancing Bias in Two-sided Markets for Fair Stable MatchingsPoster
  187. Bandit Learning in Matching Markets with IndifferencePoster
  188. Bayesian Analysis of Combinatorial Gaussian Process BanditsPoster
  189. Bayesian Experimental Design Via Contrastive DiffusionsSpotlight
  190. Bayesian Image Regression with Soft-thresholded Conditional Autoregressive PriorPoster
  191. Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving SequencesSpotlight
  192. Bayesian Regularization of Latent RepresentationPoster
  193. Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural NetworksPoster
  194. Bayesian WeakS-to-Strong from Text Classification to GenerationPoster
  195. Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit AlgorithmsPoster
  196. Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement LearningPoster
  197. BenTo: Benchmark Reduction with In-Context TransferabilityPoster
  198. Benchmarking Predictive Coding Networks -- Made SimpleSpotlight
  199. Benign Overfitting in Out-of-Distribution Generalization of Linear ModelsPoster
  200. Better autoregressive regression with LLMs via regression-aware fine-tuningSpotlight
  201. Beyond FVD: An Enhanced Evaluation Metrics for Video Generation Distribution QualityPoster
  202. Beyond Interpretability: The Gains of Feature Monosemanticity on Model RobustnessPoster
  203. Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM AttacksPoster
  204. Beyond Next Token Prediction: Patch-Level Training for Large Language ModelsSpotlight
  205. Beyond Random Augmentations: Pretraining with Hard ViewsPoster
  206. Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension abilityPoster
  207. Beyond Worst-Case Dimensionality Reduction for Sparse VectorsPoster
  208. Beyond single neurons: population response geometry in digital twins of mouse visual cortexPoster
  209. Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double ExplorationPoster
  210. Bias Mitigation in Graph Diffusion ModelsPoster
  211. Bidirectional Decoding: Improving Action Chunking via Guided Test-Time SamplingPoster
  212. BigDocs: An Open Dataset for Training Multimodal Models on Document and Code TasksPoster
  213. Binary Losses for Density Ratio EstimationPoster
  214. BinaryDM: Accurate Weight Binarization for Efficient Diffusion ModelsPoster
  215. Biologically Constrained Barrel Cortex Model Integrates Whisker Inputs and Replicates Key Brain Network DynamicsSpotlight
  216. Bisimulation Metric for Model Predictive ControlPoster
  217. BitStack: Any-Size Compression of Large Language Models in Variable Memory EnvironmentsPoster
  218. Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language RecognitionPoster
  219. BlendRL: A Framework for Merging Symbolic and Neural Policy LearningSpotlight
  220. Block-Attention for Efficient PrefillingPoster
  221. BodyGen: Advancing Towards Efficient Embodiment Co-DesignSpotlight
  222. Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language ModelsPoster
  223. Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein InteractionsSpotlight
  224. BoneMet: An Open Large-Scale Multi-Modal Murine Dataset for Breast Cancer Bone Metastasis Diagnosis and PrognosisPoster
  225. Bonsai: Gradient-free Graph Condensation for Node ClassificationPoster
  226. Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and ApproximationPoster
  227. Boosting Latent Diffusion with Perceptual ObjectivesPoster
  228. Boosting Methods for Interval-censored Data with Regression and ClassificationPoster
  229. Boosting Multiple Views for pretrained-based Continual LearningPoster
  230. Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in GamesPoster
  231. Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based PriorsSpotlight
  232. Boosting the visual interpretability of CLIP via adversarial fine-tuningPoster
  233. Bootstrapped Model Predictive ControlPoster
  234. Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss FunctionsPoster
  235. Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of ExplorationOral
  236. Brain-inspired $L_p$-Convolution benefits large kernels and aligns better with visual cortexPoster
  237. BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulationPoster
  238. BrainOOD: Out-of-distribution Generalizable Brain Network AnalysisPoster
  239. Breaking Free from MMI: A New Frontier in Rationalization by Probing Input UtilizationPoster
  240. Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent DebatePoster
  241. Breaking Neural Network Scaling Laws with ModularityPoster
  242. Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive GridsPoster
  243. Bridging Information Asymmetry in Text-video Retrieval: A Data-centric ApproachPoster
  244. Bridging the Gap Between f-divergences and Bayes Hilbert SpacesPoster
  245. Bridging the Gap between Database Search and \emph{De Novo} Peptide Sequencing with SearchNovoPoster
  246. Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function SpacePoster
  247. Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQLPoster
  248. Bringing NeRFs to the Latent Space: Inverse Graphics AutoencoderPoster
  249. Building Interactable Replicas of Complex Articulated Objects via Gaussian SplattingPoster
  250. Building, Reusing, and Generalizing Abstract Representations from Concrete SequencesPoster
  251. CAMEx: Curvature-aware Merging of ExpertsPoster
  252. CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree SearchPoster
  253. CAX: Cellular Automata Accelerated in JAXOral
  254. CBMA: Improving Conformal Prediction through Bayesian Model AveragingPoster
  255. CFD: Learning Generalized Molecular Representation via Concept-Enhanced Feedback DisentanglementPoster
  256. CHAMP: Conformalized 3D Human Multi-Hypothesis Pose EstimatorsPoster
  257. CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical SystemsPoster
  258. CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic ScreeningPoster
  259. CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained ModelsPoster
  260. CLIPDrag: Combining Text-based and Drag-based Instructions for Image EditingPoster
  261. CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot ClassificationPoster
  262. CO-MOT: Boosting End-to-end Transformer-based Multi-Object Tracking via Coopetition Label Assignment and Shadow SetsPoster
  263. COME: Test-time Adaption by Conservatively Minimizing EntropyPoster
  264. CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution ShiftsPoster
  265. CONGO: Compressive Online Gradient OptimizationPoster
  266. COPER: Correlation-based Permutations for Multi-View ClusteringSpotlight
  267. CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation LearningPoster
  268. CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain ObservationsSpotlight
  269. CSA: Data-efficient Mapping of Unimodal Features to Multimodal FeaturesPoster
  270. CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and ReasoningPoster
  271. CViT: Continuous Vision Transformer for Operator LearningPoster
  272. CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent CooperationPoster
  273. Cached Multi-Lora Composition for Multi-Concept Image GenerationPoster
  274. Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained ControlPoster
  275. Calibrating LLMs with Information-Theoretic Evidential Deep LearningPoster
  276. CameraCtrl: Enabling Camera Control for Video Diffusion ModelsPoster
  277. Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index ModelOral
  278. Can One Modality Model Synergize Training of Other Modality Models?Poster
  279. Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games?Poster
  280. Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language ModelsPoster
  281. Can We Ignore Labels in Out of Distribution Detection?Poster
  282. Can a Large Language Model be a Gaslighter?Poster
  283. Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill LearningOral
  284. Capability Localization: Capabilities Can be Localized rather than Individual KnowledgePoster
  285. Captured by Captions: On Memorization and its Mitigation in CLIP ModelsPoster
  286. CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux ModellingPoster
  287. Cauchy-Schwarz RegularizersPoster
  288. Causal Discovery via Bayesian OptimizationPoster
  289. Causal Effect Estimation with Mixed Latent Confounders and Post-treatment VariablesPoster
  290. Causal Graph Transformer for Treatment Effect Estimation Under Unknown InterferencePoster
  291. Causal Graphical Models for Vision-Language Compositional UnderstandingPoster
  292. Causal Identification for Complex Functional Longitudinal StudiesPoster
  293. Causal Information Prioritization for Efficient Reinforcement LearningPoster
  294. Causal Representation Learning from Multimodal Biomedical ObservationsPoster
  295. CausalRivers - Scaling up benchmarking of causal discovery for real-world time-seriesSpotlight
  296. Causally Motivated Sycophancy Mitigation for Large Language ModelsPoster
  297. Centrality-guided Pre-training for GraphPoster
  298. Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive ImagesSpotlight
  299. Certified Robustness Under Bounded Levenshtein DistancePoster
  300. Certifying Counterfactual Bias in LLMsPoster
  301. Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor AttacksPoster
  302. Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision ModelsPoster
  303. Chain-of-Thought Provably Enables Learning the (Otherwise) UnlearnablePoster
  304. ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart UnderstandingOral
  305. Charting the Design Space of Neural Graph Representations for Subgraph MatchingPoster
  306. CheapNet: Cross-attention on Hierarchical representations for Efficient protein-ligand binding Affinity PredictionPoster
  307. Chemistry-Inspired Diffusion with Non-Differentiable GuidancePoster
  308. Chunk-Distilled Language ModelingPoster
  309. Circuit Transformer: A Transformer That Preserves Logical EquivalencePoster
  310. CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMsPoster
  311. Class Distribution-induced Attention Map for Open-vocabulary Semantic SegmentationsPoster
  312. Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player GamesOral
  313. ClawMachine: Learning to Fetch Visual Tokens for Referential ComprehensionPoster
  314. ClimaQA: An Automated Evaluation Framework for Climate Question Answering ModelsPoster
  315. Clique Number Estimation via Differentiable Functions of Adjacency Matrix PermutationsPoster
  316. Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive DiffusionSpotlight
  317. CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-ResolutionPoster
  318. CoMotion: Concurrent Multi-person 3D MotionPoster
  319. CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMsPoster
  320. CogCoM: A Visual Language Model with Chain-of-Manipulations ReasoningPoster
  321. CollabEdit: Towards Non-destructive Collaborative Knowledge EditingPoster
  322. Collaborative Discrete-Continuous Black-Box Prompt Learning for Language ModelsPoster
  323. Collapsed Language Models Promote FairnessPoster
  324. ComPC: Completing a 3D Point Cloud with 2D Diffusion PriorsPoster
  325. ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift RegularizationPoster
  326. Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File SelectionOral
  327. Comparing Targeting Strategies for Maximizing Social Welfare with Limited ResourcesPoster
  328. Competitive Fair Scheduling with PredictionsPoster
  329. Complementary Label Learning with Positive Label Guessing and Negative Label EnhancementPoster
  330. Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed SmoothnessPoster
  331. Composing Unbalanced Flows for Flexible Docking and RelaxationOral
  332. Compositional Entailment Learning for Hyperbolic Vision-Language ModelsOral
  333. Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer ModelsPoster
  334. Compute-Optimal LLMs Provably Generalize Better with ScalePoster
  335. ConMix: Contrastive Mixup at Representation Level for Long-tailed Deep ClusteringPoster
  336. ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud RestorationPoster
  337. Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease StudiesSpotlight
  338. Confidence Elicitation: A New Attack Vector for Large Language ModelsPoster
  339. Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement LearningPoster
  340. Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy FilteringPoster
  341. Conformal Language Model Reasoning with Coherent FactualityPoster
  342. Conformal Structured PredictionPoster
  343. Conformalized Survival Analysis for General Right-Censored DataPoster
  344. Connecting Federated ADMM to BayesPoster
  345. Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic InformationPoster
  346. Conservative Contextual Bandits: Beyond Linear RepresentationsPoster
  347. Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement LearningPoster
  348. Constructing Confidence Intervals for Average Treatment Effects from Multiple DatasetsPoster
  349. Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent DimensionsPoster
  350. Context Steering: Controllable Personalization at Inference TimePoster
  351. Context-aware Dynamic Pruning for Speech Foundation ModelsPoster
  352. Contextualizing biological perturbation experiments through languagePoster
  353. Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to AdaptPoster
  354. Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from ImagesPoster
  355. Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech SynthesisPoster
  356. Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEsSpotlight
  357. ContraDiff: Planning Towards High Return States via Contrastive LearningPoster
  358. Controllable Blur Data Augmentation Using 3D-Aware Motion EstimationPoster
  359. Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety RequirementsPoster
  360. Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental ControlPoster
  361. ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback EnvironmentsPoster
  362. Convergence of Distributed Adaptive Optimization with Local UpdatesPoster
  363. Convex Formulations for Training Two-Layer ReLU Neural NetworksPoster
  364. Coreset Selection via Reducible Loss in Continual LearningPoster
  365. Coreset Spectral ClusteringPoster
  366. Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)Poster
  367. Correlation and Navigation in the Vocabulary Key Representation Space of Language ModelsPoster
  368. Counterfactual Generative Modeling with Variational Causal InferencePoster
  369. Credal Wrapper of Model Averaging for Uncertainty Estimation in ClassificationSpotlight
  370. Credit-based self organizing maps: training deep topographic networks with minimal performance degradationPoster
  371. Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative ModelsPoster
  372. Cross-Domain Off-Policy Evaluation and Learning for Contextual BanditsPoster
  373. CryoFM: A Flow-based Foundation Model for Cryo-EM DensitiesPoster
  374. CryoGEN: Generative Energy-based Models for Cryogenic Electron Tomography ReconstructionPoster
  375. CtD: Composition through Decomposition in Emergent CommunicationPoster
  376. Curriculum-aware Training for Discriminating Molecular Property Prediction ModelsPoster
  377. CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body GenerationOral
  378. Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object DetectionPoster
  379. DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language ModelsPoster
  380. DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video GenerationPoster
  381. DECO: Unleashing the Potential of ConvNets for Query-based Detection and SegmentationPoster
  382. DICE: Data Influence Cascade in Decentralized LearningPoster
  383. DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max OptimizationSpotlight
  384. DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language ModelsPoster
  385. DPaI: Differentiable Pruning at Initialization with Node-Path Balance PrinciplePoster
  386. DRL: Decomposed Representation Learning for Tabular Anomaly DetectionPoster
  387. DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of ConstraintsPoster
  388. DRoP: Distributionally Robust Data PruningSpotlight
  389. DUALFormer: Dual Graph TransformerPoster
  390. DUET: Decentralized Bilevel Optimization without Lower-Level Strong ConvexityPoster
  391. Data Center Cooling System Optimization Using Offline Reinforcement LearningPoster
  392. Data Distillation for extrapolative protein design through exact preference optimizationPoster
  393. Data Unlearning in Diffusion ModelsPoster
  394. Data-centric Prediction Explanation via Kernelized Stein DiscrepancyPoster
  395. Dataset Ownership Verification in Contrastive Pre-trained ModelsPoster
  396. Debiasing Federated Learning with Correlated Client ParticipationPoster
  397. Decentralized Optimization with Coupled ConstraintsPoster
  398. Decision Information Meets Large Language Models: The Future of Explainable Operations ResearchPoster
  399. Decision Tree Induction Through LLMs via Semantically-Aware EvolutionPoster
  400. Deconstructing What Makes a Good Optimizer for Autoregressive Language ModelsPoster
  401. Decoupled Finetuning for Domain Generalizable Semantic SegmentationPoster
  402. Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic GraphsPoster
  403. Decoupled Subgraph Federated LearningPoster
  404. Decoupling Angles and Strength in Low-rank AdaptationPoster
  405. Decoupling Layout from Glyph in Online Chinese Handwriting GenerationPoster
  406. Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEsPoster
  407. Deep Kernel Posterior Learning under Infinite Variance Prior WeightsPoster
  408. Deep Kernel Relative Test for Machine-generated Text DetectionPoster
  409. Deep Networks Learn Features From Local Discontinuities in the Label FunctionPoster
  410. Deep Random Features for Scalable Interpolation of Spatiotemporal DataPoster
  411. Deep Signature: Characterization of Large-Scale Molecular DynamicsPoster
  412. DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RLOral
  413. DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural NetworksPoster
  414. DeeperForward: Enhanced Forward-Forward Training for Deeper and Better PerformancePoster
  415. Democratic Training Against Universal Adversarial PerturbationsPoster
  416. Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-PassingPoster
  417. Denoising Autoregressive Transformers for Scalable Text-to-Image GenerationPoster
  418. DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual GroundingPoster
  419. Density estimation with LLMs: a geometric investigation of in-context learning trajectoriesPoster
  420. Descent with Misaligned Gradients and Applications to Hidden ConvexityPoster
  421. Designing Concise ConvNets with Columnar StagesPoster
  422. Designing Mechanical Meta-Materials by Learning Equivariant FlowsPoster
  423. Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion ModelsPoster
  424. Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve RenderingPoster
  425. DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic RefinementPoster
  426. Difference-of-submodular Bregman DivergencePoster
  427. Differentiable Causal Discovery for Latent Hierarchical Causal ModelsPoster
  428. Differentiable Rule Induction from Raw Sequence InputsPoster
  429. Differentiable and Learnable Wireless Simulation with Geometric TransformersPoster
  430. Differentially Private Federated Learning with Time-Adaptive Privacy SpendingPoster
  431. Differentially Private Steering for Large Language Model AlignmentPoster
  432. Differentially private learners for heterogeneous treatment effectsPoster
  433. Differentially private optimization for non-decomposable objective functionsPoster
  434. Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter TuningPoster
  435. Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion ModelsSpotlight
  436. Diffusion Bridge AutoEncoders for Unsupervised Representation LearningSpotlight
  437. Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology ImagesPoster
  438. Diffusion Transformers for Tabular Data Time Series GenerationPoster
  439. Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion ModelsPoster
  440. Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series ForecastingPoster
  441. Digi-Q: Learning VLM Q-Value Functions for Training Device-Control AgentsPoster
  442. Dimension Agnostic Neural ProcessesPoster
  443. Direct Distributional Optimization for Provable Alignment of Diffusion ModelsPoster
  444. Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training DemonstrationsSpotlight
  445. Directional Gradient Projection for Robust Fine-Tuning of Foundation ModelsPoster
  446. Discovering Group Structures via Unitary Representation LearningPoster
  447. Discovering Influential Neuron Path in Vision TransformersPoster
  448. Discovering Temporally Compositional Neural Manifolds with Switching Infinite GPFASpotlight
  449. Discrete Codebook World Models for Continuous ControlPoster
  450. Discrete Distribution NetworksPoster
  451. Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal ControlPoster
  452. Discrete Latent Plans via Semantic Skill AbstractionsPoster
  453. Discretization-invariance? On the Discretization Mismatch Errors in Neural OperatorsPoster
  454. Disentangled Representation Learning with the Gromov-Monge GapPoster
  455. Disentangling 3D Animal Pose Dynamics with Scrubbed Conditional Latent VariablesPoster
  456. Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance ConstraintPoster
  457. DistillHGNN: A Knowledge Distillation Approach for High-Speed Hypergraph Neural NetworksPoster
  458. Distilling Dataset into Neural FieldPoster
  459. Distilling Reinforcement Learning Algorithms for In-Context Model-Based PlanningPoster
  460. Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion DistillationPoster
  461. Distribution-Specific Agnostic Conditional Classification With HalfspacesPoster
  462. Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention LayersPoster
  463. Divergence of Neural Tangent Kernel in Classification ProblemsPoster
  464. Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic GamesPoster
  465. Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation LearningPoster
  466. Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale BenchmarkPoster
  467. Do LLMs estimate uncertainty well in instruction-following?Poster
  468. Do Large Language Models Truly Understand Geometric Structures?Poster
  469. Do Mice Grok? Glimpses of Hidden Progress in Sensory CortexPoster
  470. Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum MechanismPoster
  471. Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under AmbiguitiesOral
  472. Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete GeneratorsPoster
  473. Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble DecodingPoster
  474. DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement LearningPoster
  475. Dobi-SVD: Differentiable SVD for LLM Compression and Some New PerspectivesPoster
  476. DocMIA: Document-Level Membership Inference Attacks against DocVQA ModelsPoster
  477. Does Training with Synthetic Data Truly Protect Privacy?Poster
  478. Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language ModelsPoster
  479. Doubly robust identification of treatment effects from multiple environmentsPoster
  480. DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity PreservationPoster
  481. DreamDistribution: Learning Prompt Distribution for Diverse In-distribution GenerationPoster
  482. Dreamweaver: Learning Compositional World Models from PixelsPoster
  483. Durable Quantization Conditioned Misalignment Attack on Large Language ModelsPoster
  484. DyCAST: Learning Dynamic Causal Structure from Time SeriesPoster
  485. DynAlign: Unsupervised Dynamic Taxonomy Alignment for Cross-Domain SegmentationPoster
  486. DynFrs: An Efficient Framework for Machine Unlearning in Random ForestPoster
  487. DynaPrompt: Dynamic Test-Time Prompt TuningPoster
  488. Dynamic Assortment Selection and Pricing with Censored Preference FeedbackPoster
  489. Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length AdjustmentPoster
  490. Dynamic Loss-Based Sample Reweighting for Improved Large Language Model PretrainingPoster
  491. Dynamic Low-Rank Sparse Adaptation for Large Language ModelsPoster
  492. Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of ExpertsPoster
  493. Dynamic Negative Guidance of Diffusion ModelsPoster
  494. Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction DefensePoster
  495. Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption RobustnessPoster
  496. DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic ScenesSpotlight
  497. E(3)-equivariant models cannot learn chirality: Field-based molecular generationPoster
  498. EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice RoutingPoster
  499. EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior GenerationPoster
  500. ECD: A Machine Learning Benchmark for Predicting Enhanced-Precision Electronic Charge Density in Crystalline Inorganic MaterialsOral
  501. EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language ModelsPoster
  502. EFFICIENT JAILBREAK ATTACK SEQUENCES ON LARGE LANGUAGE MODELS VIA MULTI-ARMED BANDIT-BASED CONTEXT SWITCHINGPoster
  503. ELBOing Stein: Variational Bayes with Stein Mixture InferencePoster
  504. ELFS: Label-Free Coreset Selection with Proxy Training DynamicsPoster
  505. ELICIT: LLM Augmentation Via External In-context CapabilityPoster
  506. EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical AlignmentPoster
  507. ESE: Espresso Sentence EmbeddingsPoster
  508. EVA: Geometric Inverse Design for Fast Protein Motif-Scaffolding with Coupled FlowPoster
  509. Easing Training Process of Rectified Flow Models Via Lengthening Inter-Path DistanceSpotlight
  510. EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face GenerationPoster
  511. Edge Prompt Tuning for Graph Neural NetworksPoster
  512. Edge-aware Image Smoothing with Relative Wavelet Domain RepresentationPoster
  513. EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout EditingPoster
  514. Effective and Efficient Time-Varying Counterfactual Prediction with State-Space ModelsPoster
  515. Effective post-training embedding compression via temperature control in contrastive trainingSpotlight
  516. Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPsPoster
  517. Efficient Biological Data Acquisition through Inference Set DesignPoster
  518. Efficient Causal Decision Making with One-sided FeedbackPoster
  519. Efficient Cross-Episode Meta-RLPoster
  520. Efficient Discovery of Pareto Front for Multi-Objective Reinforcement LearningPoster
  521. Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMaxPoster
  522. Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetsPoster
  523. Efficient Exploration and Discriminative World Model Learning with an Object-Centric AbstractionPoster
  524. Efficient Imitation under MisspecificationPoster
  525. Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIsPoster
  526. Efficient Learning with Sine-Activated Low-Rank MatricesPoster
  527. Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-TrainingPoster
  528. Efficient Model Editing with Task-Localized Sparse Fine-tuningPoster
  529. Efficient Model-Based Reinforcement Learning Through Optimistic Thompson SamplingPoster
  530. Efficient Neuron Segmentation in Electron Microscopy by Affinity-Guided QueriesPoster
  531. Efficient Off-Policy Learning for High-Dimensional Action SpacesPoster
  532. Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form GamesPoster
  533. Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language ModelsPoster
  534. Efficient Sparse PCA via Block-DiagonalizationPoster
  535. Efficient Top-m Data Values Identification for Data SelectionPoster
  536. Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language ModelPoster
  537. Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based CoresetsPoster
  538. EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric VideosPoster
  539. EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal ConditioningPoster
  540. Emergent Orientation Maps —— Mechanisms, Coding Efficiency and RobustnessSpotlight
  541. End-to-end Learning of Gaussian Mixture Priors for Diffusion SamplerPoster
  542. Endowing Visual Reprogramming with Adversarial RobustnessPoster
  543. Energy-Weighted Flow Matching for Offline Reinforcement LearningPoster
  544. Energy-based Backdoor Defense Against Federated Graph LearningOral
  545. Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded BoundaryPoster
  546. Enhanced Diffusion Sampling via Extrapolation with Multiple ODE SolutionsPoster
  547. Enhancing Clustered Federated Learning: Integration of Strategies and Improved MethodologiesPoster
  548. Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized DataPoster
  549. Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout InformationPoster
  550. Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-TuningPoster
  551. Enhancing Graph Of Thought: Enhancing Prompts with LLM Rationales and Dynamic Temperature ControlPoster
  552. Enhancing Pre-trained Representation Classifiability can Boost its InterpretabilitySpotlight
  553. Enhancing Prediction Performance through Influence MeasurePoster
  554. Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision LayerPoster
  555. Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular SystemsSpotlight
  556. Ensembles of Low-Rank Expert AdaptersPoster
  557. Entropy-based Activation Function Optimization: A Method on Searching Better Activation FunctionsPoster
  558. Episodic Novelty Through Temporal DistancePoster
  559. Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion ModelsPoster
  560. Equivariant Masked Position Prediction for Efficient Molecular RepresentationPoster
  561. Equivariant Neural Functional Networks for TransformersPoster
  562. Estimation of single-cell and tissue perturbation effect in spatial transcriptomics via Spatial Causal DisentanglementPoster
  563. EvA: Erasing Spurious Correlations with ActivationsPoster
  564. Event-Driven Online Vertical Federated LearningPoster
  565. Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?Poster
  566. Evidential Learning-based Certainty Estimation for Robust Dense Feature MatchingPoster
  567. Exact Certification of (Graph) Neural Networks Against Label PoisoningSpotlight
  568. Exact Computation of Any-Order Shapley Interactions for Graph Neural NetworksPoster
  569. Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypesPoster
  570. Execution-guided within-prompt search for programming-by-examplePoster
  571. Expected Return SymmetriesPoster
  572. Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention FormulationPoster
  573. Explanations of GNN on Evolving Graphs via Axiomatic Layer edgesPoster
  574. Exploiting Distribution Constraints for Scalable and Efficient Image RetrievalPoster
  575. Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-NormPoster
  576. Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction RankPoster
  577. Exploring Learning Complexity for Efficient Downstream Dataset PruningPoster
  578. Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing RobustnessPoster
  579. Exploring a Principled Framework for Deep Subspace ClusteringPoster
  580. Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networksPoster
  581. Exploring the Camera Bias of Person Re-identificationSpotlight
  582. Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement LearningPoster
  583. Extendable and Iterative Structure Learning Strategy for Bayesian NetworksPoster
  584. F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AIPoster
  585. FACTS: A Factored State-Space Framework for World ModellingPoster
  586. FIG: Flow with Interpolant Guidance for Linear Inverse ProblemsPoster
  587. FIRING-Net: A filtered feature recycling network for speech enhancementPoster
  588. FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World ModelPoster
  589. FLOPS: Forward Learning with OPtimal SamplingPoster
  590. FOSP: Fine-tuning Offline Safe Policy through World ModelsPoster
  591. Factor Graph-based Interpretable Neural NetworksPoster
  592. Fair Clustering in the Sliding Window ModelSpotlight
  593. FairDen: Fair Density-Based ClusteringPoster
  594. FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"Poster
  595. Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target GenerationPoster
  596. Fast Uncovering of Protein Sequence Diversity from StructureSpotlight
  597. Fast and Accurate Blind Flexible DockingPoster
  598. Fast and Slow Streams for Online Time Series Forecasting Without Information LeakagePoster
  599. Fast unsupervised ground metric learning with tree-Wasserstein distancePoster
  600. Faster Diffusion Sampling with Randomized Midpoints: Sequential and ParallelPoster
  601. Faster Inference of Flow-Based Generative Models via Improved Data-Noise CouplingPoster
  602. Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse PoliciesPoster
  603. Feature Responsiveness Scores: Model-Agnostic Explanations for RecoursePoster
  604. FedLWS: Federated Learning with Adaptive Layer-wise Weight ShrinkingPoster
  605. FedTMOS: Efficient One-Shot Federated Learning with Tsetlin MachinePoster
  606. Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and BeyondPoster
  607. Federated Domain Generalization with Data-free On-server Matching GradientPoster
  608. Federated Few-Shot Class-Incremental LearningPoster
  609. Federated Granger Causality Learning For Interdependent Clients With State Space RepresentationPoster
  610. Federated Residual Low-Rank Adaptation of Large Language ModelsPoster
  611. Feedback Schrödinger Bridge MatchingOral
  612. Ferret-UI 2: Mastering Universal User Interface Understanding Across PlatformsPoster
  613. Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty MeasurementPoster
  614. Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced DatasetPoster
  615. Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite LearningPoster
  616. Field-DiT: Diffusion Transformer on Unified Video, 3D, and Game Field GenerationPoster
  617. Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language ModelsPoster
  618. Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL AssortmentPoster
  619. Find A Winning Sign: Sign Is All We Need to Win the LotteryPoster
  620. Finding Shared Decodable Concepts and their Negations in the BrainPoster
  621. Fitting Networks with a Cancellation TrickPoster
  622. Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and BeyondPoster
  623. FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement LearningPoster
  624. Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching PriorsPoster
  625. Flow-based Variational Mutual Information: Fast and Flexible ApproximationsPoster
  626. Flow: Modularized Agentic Workflow AutomationPoster
  627. FlowDec: A flow-based full-band general audio codec with high perceptual qualityPoster
  628. For Better or For Worse? Learning Minimum Variance Features With Label AugmentationPoster
  629. Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced ExplorationPoster
  630. Forget the Data and Fine-Tuning! Just Fold the Network to CompressPoster
  631. FormalAlign: Automated Alignment Evaluation for AutoformalizationPoster
  632. Forte : Finding Outliers with Representation Typicality EstimationPoster
  633. Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation ModelsPoster
  634. FreSh: Frequency Shifting for Accelerated Neural Representation LearningPoster
  635. Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra CostsPoster
  636. FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force FieldsPoster
  637. FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian NoisePoster
  638. Frequency-Guided Masking for Enhanced Vision Self-Supervised LearningPoster
  639. From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic DataPoster
  640. From Attention to Activation: Unraveling the Enigmas of Large Language ModelsPoster
  641. From Commands to Prompts: LLM-based Semantic File System for AIOSPoster
  642. From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQPoster
  643. From GNNs to Trees: Multi-Granular Interpretability for Graph Neural NetworksPoster
  644. From Layers to States: A State Space Model Perspective to Deep Neural Network Layer DynamicsPoster
  645. From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-AnsweringPoster
  646. From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual ModalitiesPoster
  647. From Promise to Practice: Realizing High-performance Decentralized TrainingPoster
  648. From Search to Sampling: Generative Models for Robust Algorithmic RecoursePoster
  649. From Tokens to Lattices: Emergent Lattice Structures in Language ModelsPoster
  650. From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal JunglePoster
  651. Fugatto 1: Foundational Generative Audio Transformer Opus 1Poster
  652. Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak AttacksPoster
  653. GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D GenerationPoster
  654. GANDALF: Generative AttentioN based Data Augmentation and predictive modeLing Framework for personalized cancer treatmentPoster
  655. GETS: Ensemble Temperature Scaling for Calibration in Graph Neural NetworksSpotlight
  656. GLOMA: Global Video Text Spotting with Morphological AssociationPoster
  657. GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in GraphsPoster
  658. GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits LearningPoster
  659. GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set MatchingPoster
  660. GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial AttacksPoster
  661. GRAIN: Exact Graph Reconstruction from GradientsPoster
  662. GSBA$^K$: $top$-$K$ Geometric Score-based Black-box AttackPoster
  663. GSE: Group-wise Sparse and Explainable Adversarial AttacksPoster
  664. GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented UnderstandingPoster
  665. Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic TeacherPoster
  666. Gaussian Differentially Private Human Faces Under a Face Radial Curve RepresentationPoster
  667. Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional, Black-box SystemsPoster
  668. Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture WarpingPoster
  669. Gaussian Mixture Counterfactual GeneratorPoster
  670. Gaussian Splatting Lucas-KanadePoster
  671. Gaussian-Based Instance-Adaptive Intensity Modeling for Point-Supervised Facial Expression SpottingPoster
  672. GaussianAnything: Interactive Point Cloud Flow Matching for 3D GenerationPoster
  673. GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and GaussiansPoster
  674. GeSubNet: Gene Interaction Inference for Disease Subtype Network GenerationOral
  675. GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time AlignmentPoster
  676. GenDataAgent: On-the-fly Dataset Augmentation with Synthetic DataPoster
  677. GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEsPoster
  678. General Scene Adaptation for Vision-and-Language NavigationPoster
  679. Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive PowerPoster
  680. Generalizable Motion Planning via Operator LearningPoster
  681. Generalization Bounds for Canonicalization: A Comparative Study with Group AveragingPoster
  682. Generalization and Distributed Learning of GFlowNetsPoster
  683. Generalization in VAE and Diffusion Models: A Unified Information-Theoretic AnalysisPoster
  684. Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining DataPoster
  685. Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed GraphsPoster
  686. Generalized Video Moment RetrievalPoster
  687. Generalizing Reasoning Problems to Longer LengthsPoster
  688. Generalizing Weisfeiler-Lehman Kernels to SubgraphsPoster
  689. Generating Graphs via Spectral DiffusionPoster
  690. Generating Likely Counterfactuals Using Sum-Product NetworksPoster
  691. Generating Physical Dynamics under PriorsPoster
  692. Generation and Comprehension Hand-in-Hand: Vision-guided Expression Diffusion for Boosting Referring Expression Generation and ComprehensionPoster
  693. Generator Matching: Generative modeling with arbitrary Markov processesOral
  694. GeoILP: A Synthetic Dataset to Guide Large-Scale Rule InductionPoster
  695. GeoLoRA: Geometric integration for parameter efficient fine-tuningPoster
  696. Geometric Inductive Biases of Deep Networks: The Role of Data and ArchitectureSpotlight
  697. Geometry of Long-Tailed Representation Learning: Rebalancing Features for Skewed DistributionsPoster
  698. Geometry of Neural Reinforcement Learning in Continuous State and Action SpacesOral
  699. Geometry-aware RL for Manipulation of Varying Shapes and Deformable ObjectsOral
  700. Global Convergence in Neural ODEs: Impact of Activation FunctionsOral
  701. Global Convergence of Policy Gradient in Average Reward MDPsPoster
  702. Global Identifiability of Overcomplete Dictionary Learning via L1 and Volume MinimizationPoster
  703. Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box TransformersPoster
  704. Going Beyond Static: Understanding Shifts with Time-Series AttributionPoster
  705. GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene SupervisionSpotlight
  706. Gradient correlation is a key ingredient to accelerate SGD with momentumPoster
  707. Gradient-Free Generation for Hard-Constrained SystemsPoster
  708. Grammar Reinforcement Learning: path and cycle counting in graphs with a Context-Free Grammar and Transformer approachPoster
  709. Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow SchedulingPoster
  710. Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral PerspectivePoster
  711. Graph Neural Networks Can (Often) Count SubstructuresSpotlight
  712. Graph Transformers Dream of Electric FlowPoster
  713. Graph-based Document Structure AnalysisPoster
  714. GraphBridge: Towards Arbitrary Transfer Learning in GNNsPoster
  715. GraphEval: A Lightweight Graph-Based LLM Framework for Idea EvaluationPoster
  716. Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and AttentionPoster
  717. Grounding Multimodal Large Language Model in GUI WorldPoster
  718. Group-robust Sample Reweighting for Subpopulation Shifts via Influence FunctionsPoster
  719. Gumbel Counterfactual Generation From Language ModelsPoster
  720. HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNSPoster
  721. HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASRPoster
  722. HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied AgentsPoster
  723. HELMET: How to Evaluate Long-context Models Effectively and ThoroughlyPoster
  724. HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model FinetuningPoster
  725. HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual AdaptersPoster
  726. HQ-Edit: A High-Quality Dataset for Instruction-based Image EditingPoster
  727. HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded ScenesPoster
  728. HShare: Fast LLM Decoding by Hierarchical Key-Value SharingPoster
  729. HaDeMiF: Hallucination Detection and Mitigation in Large Language ModelsPoster
  730. Halton Scheduler for Masked Generative Image TransformerPoster
  731. Has the Deep Neural Network learned the Stochastic Process? An Evaluation ViewpointPoster
  732. Have the VLMs Lost Confidence? A Study of Sycophancy in VLMsPoster
  733. Heavy-Tailed Diffusion with Denoising Levy Probabilistic ModelsPoster
  734. Hessian-Free Online Certified UnlearningPoster
  735. HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model DebuggingPoster
  736. Hidden in the Noise: Two-Stage Robust Watermarking for ImagesPoster
  737. Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language ModelsPoster
  738. Hierarchically Encapsulated Representation for Protocol Design in Self-Driving LabsPoster
  739. High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational AutoencodersPoster
  740. High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian RepresentationOral
  741. High-dimension Prototype is a Better Incremental Object Detection LearnerPoster
  742. High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.Poster
  743. Holistically Evaluating the Environmental Impact of Creating Language ModelsSpotlight
  744. Homomorphism Counts as Structural Encodings for Graph LearningPoster
  745. Homomorphism Expressivity of Spectral Invariant Graph Neural NetworksOral
  746. Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic SelectionPoster
  747. How DNNs break the Curse of Dimensionality: Compositionality and Symmetry LearningPoster
  748. How Gradient descent balances features: A dynamical analysis for two-layer neural networksPoster
  749. How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric EncodingsPoster
  750. How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node EmbeddingsPoster
  751. How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion.Poster
  752. How much of my dataset did you use? Quantitative Data Usage Inference in Machine LearningOral
  753. How new data permeates LLM knowledge and how to dilute itSpotlight
  754. How to Find the Exact Pareto Front for Multi-Objective MDPs?Spotlight
  755. How to Probe: Simple Yet Effective Techniques for Improving Post-hoc ExplanationsPoster
  756. How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for DistributionsPoster
  757. Human-inspired Episodic Memory for Infinite Context LLMsPoster
  758. Hummingbird: High Fidelity Image Generation via Multimodal Context AlignmentPoster
  759. HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy GenerationPoster
  760. Hybrid Regularization Improves Diffusion-based Inverse Problem SolvingPoster
  761. HyperDAS: Towards Automating Mechanistic Interpretability with HypernetworksPoster
  762. HyperPLR: Hypergraph Generation through Projection, Learning, and ReconstructionPoster
  763. Hyperbolic Genome EmbeddingsPoster
  764. I-Con: A Unifying Framework for Representation LearningPoster
  765. ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake DatasetPoster
  766. IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt LearningPoster
  767. INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge GraphPoster
  768. INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement LearningPoster
  769. Identifiability for Gaussian Processes with Holomorphic KernelsPoster
  770. Identification of Intermittent Temporal Latent ProcessPoster
  771. Identifying latent state transitions in non-linear dynamical systemsPoster
  772. Image-level Memorization Detection via Inversion-based Inference PerturbationPoster
  773. Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate RegressionSpotlight
  774. Implicit Neural Surface Deformation with Explicit Velocity FieldsPoster
  775. Implicit Search via Discrete Diffusion: A Study on ChessPoster
  776. Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity AssumptionsPoster
  777. Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear ExtensionSpotlight
  778. Improved Diffusion-based Generative Model with Better Adversarial RobustnessPoster
  779. Improved Sampling Algorithms for Lévy-Itô Diffusion ModelsPoster
  780. Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization ApproachPoster
  781. Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex OptimizationSpotlight
  782. Improving Deep Regression with TightnessPoster
  783. Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding AttacksPoster
  784. Improving Language Model Distillation through Hidden State MatchingPoster
  785. Improving Large Language Model Planning with Action Sequence SimilarityPoster
  786. Improving Neural Network Accuracy by Concurrently Training with a Twin NetworkPoster
  787. Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance MatchingOral
  788. Improving Reasoning Performance in Large Language Models via Representation EngineeringPoster
  789. Improving Unsupervised Constituency Parsing via Maximizing Semantic InformationSpotlight
  790. Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression EfficiencySpotlight
  791. InCoDe: Interpretable Compressed Descriptions For Image GenerationPoster
  792. Incorporating Visual Correspondence into Diffusion Model for Virtual Try-OnPoster
  793. Incremental Causal Effect for Time to Treatment InitializationPoster
  794. Inference Optimal VLMs Need Fewer Visual Tokens and More ParametersPoster
  795. Infilling Score: A Pretraining Data Detection Algorithm for Large Language ModelsPoster
  796. Influence-Guided Diffusion for Dataset DistillationPoster
  797. InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information ShapingPoster
  798. Injective flows for star-like manifoldsPoster
  799. Inner Information Analysis Algorithm for Deep Neural Network based on CommunityPoster
  800. Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-InstructPoster
  801. InstaRevive: One-Step Image Enhancement via Dynamic Score MatchingPoster
  802. InstaSHAP: Interpretable Additive Models Explain Shapley Values InstantlyPoster
  803. InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective DistillationPoster
  804. Integral Performance Approximation for Continuous-Time Reinforcement Learning ControlPoster
  805. Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic FlowsPoster
  806. Interactive Adjustment for Human Trajectory Prediction with Individual FeedbackPoster
  807. Interpretable Causal Representation Learning for Biological Data in the Pathway SpacePoster
  808. Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light ScenariosPoster
  809. Interpreting Emergent Planning in Model-Free Reinforcement LearningOral
  810. Interpreting Language Reward Models via Contrastive ExplanationsPoster
  811. Intrinsic User-Centric Interpretability through Global Mixture of ExpertsPoster
  812. Inverse Attention Agents for Multi-Agent SystemsPoster
  813. Inverse Rendering using Multi-Bounce Path Tracing and Reservoir SamplingPoster
  814. InversionGNN: A Dual Path Network for Multi-Property Molecular OptimizationPoster
  815. InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemmaPoster
  816. Investigating Pattern Neurons in Urban Time Series ForecastingPoster
  817. Is Your Multimodal Language Model Oversensitive to Safe Queries?Poster
  818. Is Your Video Language Model a Reliable Judge?Poster
  819. Is uniform expressivity too restrictive? Towards efficient expressivity of GNNsPoster
  820. Isometric Regularization for Manifolds of Functional DataPoster
  821. It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale OptimisationPoster
  822. IterGen: Iterative Semantic-aware Structured LLM Generation with BacktrackingPoster
  823. Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information BottleneckPoster
  824. JPEG Inspired Deep LearningPoster
  825. Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear ComplexityPoster
  826. Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective OptimizationSpotlight
  827. Joint Graph Rewiring and Feature Denoising via Spectral ResonanceOral
  828. Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves AlignmentSpotlight
  829. K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language ModelsPoster
  830. KGARevion: An AI Agent for Knowledge-Intensive Biomedical QAPoster
  831. KLay: Accelerating Arithmetic Circuits for Neurosymbolic AIPoster
  832. Kernel-based Optimally Weighted Conformal Time-Series PredictionPoster
  833. KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction KineticsPoster
  834. KinPFN: Bayesian Approximation of RNA Folding Kinetics using Prior-Data Fitted NetworksPoster
  835. KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series ForecastingPoster
  836. L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and EnhancementPoster
  837. L3Ms — Lagrange Large Language ModelsPoster
  838. LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement LearningPoster
  839. LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-MeshPoster
  840. LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge BasesPoster
  841. LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression ComprehensionPoster
  842. LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight SharingPoster
  843. LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal ModelsSpotlight
  844. LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth EfficientlyPoster
  845. LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation ModelsPoster
  846. Lambda-Skip Connections: the architectural component that prevents Rank CollapsePoster
  847. Language Agents Meet Causality -- Bridging LLMs and Causal World ModelsPoster
  848. Language Models Are Implicitly ContinuousPoster
  849. Language Models are Advanced AnonymizersPoster
  850. Language-Assisted Feature Transformation for Anomaly DetectionPoster
  851. Laplace Sample Information: Data Informativeness Through a Bayesian LensPoster
  852. Large (Vision) Language Models are Unsupervised In-Context LearnersPoster
  853. Large Language Models Meet Symbolic Provers for Logical Reasoning EvaluationPoster
  854. Large Language Models Often Say One Thing and Do AnotherPoster
  855. Large Language Models are Interpretable LearnersPoster
  856. Large Language Models can Become Strong Self-DetoxifiersPoster
  857. Last Iterate Convergence of Incremental Methods as a Model of ForgettingPoster
  858. Latent Radiance Fields with 3D-aware 2D RepresentationsPoster
  859. Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement LearningPoster
  860. Lawma: The Power of Specialization for Legal AnnotationPoster
  861. LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph GenerationSpotlight
  862. LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion ModelsSpotlight
  863. Learn hybrid prototypes for multivariate time series anomaly detectionPoster
  864. Learned Reference-based Diffusion Sampler for multi-modal distributionsPoster
  865. Learning Causal Alignment for Reliable Disease DiagnosisPoster
  866. Learning Chaos In A Linear WayPoster
  867. Learning Diagrams: A Graphical Language for Compositional Training RegimesPoster
  868. Learning Dynamics of Deep Matrix Factorization Beyond the Edge of StabilityPoster
  869. Learning Efficient Positional Encodings with Graph Neural NetworksPoster
  870. Learning Equivariant Non-Local Electron Density FunctionalsSpotlight
  871. Learning Gain Map for Inverse Tone MappingPoster
  872. Learning Geometric Reasoning Networks For Robot Task And Motion PlanningPoster
  873. Learning Graph Invariance by Harnessing SpuriosityPoster
  874. Learning Graph Quantized TokenizersPoster
  875. Learning Hierarchical Polynomials of Multiple Nonlinear FeaturesPoster
  876. Learning High-Degree Parities: The Crucial Role of the InitializationPoster
  877. Learning Interleaved Image-Text Comprehension in Vision-Language Large ModelsPoster
  878. Learning Mask Invariant Mutual Information for Masked Image ModelingPoster
  879. Learning Neural Networks with Distribution Shift: Efficiently Certifiable GuaranteesPoster
  880. Learning Partial Graph Matching via Optimal Partial TransportPoster
  881. Learning Randomized Algorithms with TransformersOral
  882. Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement LearningPoster
  883. Learning Spatiotemporal Dynamical Systems from Point Process ObservationsSpotlight
  884. Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement LearningPoster
  885. Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal TransportPoster
  886. Learning Structured Universe Graph with Outlier OOD Detection for Partial MatchingPoster
  887. Learning Successor Features with Distributed Hebbian Temporal MemoryPoster
  888. Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement LearningPoster
  889. Learning Transformer-based World Models with Contrastive Predictive CodingSpotlight
  890. Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive TransformerPoster
  891. Learning View-invariant World Models for Visual Robotic ManipulationPoster
  892. Learning a Fast Mixing Exogenous Block MDP using a Single TrajectoryPoster
  893. Learning and aligning single-neuron invariance manifolds in visual cortexOral
  894. Learning from End User Data with Shuffled Differential Privacy over Kernel DensitiesSpotlight
  895. Learning from negative feedback, or positive feedback or bothSpotlight
  896. Learning from weak labelers as constraintsPoster
  897. Learning mirror maps in policy mirror descentPoster
  898. Learning on One Mode: Addressing Multi-modality in Offline Reinforcement LearningPoster
  899. Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio TestPoster
  900. Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain AdaptationPoster
  901. Learning to Discover Regulatory Elements for Gene Expression PredictionOral
  902. Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial OptimizationPoster
  903. Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy LabelsPoster
  904. Learning to Help in Multi-Class SettingsPoster
  905. Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem SolvingPoster
  906. Learning to Search from Demonstration SequencesOral
  907. Learning to Select Nodes in Branch and Bound with Sufficient Tree RepresentationPoster
  908. Learning to engineer protein flexibilityPoster
  909. Learning under Temporal Label NoisePoster
  910. Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernelsSpotlight
  911. Learning-Augmented Frequent DirectionsSpotlight
  912. Learning-Augmented Search Data StructuresPoster
  913. Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop SchedulingPoster
  914. Leave-One-Out Stable Conformal PredictionPoster
  915. Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion ModelsPoster
  916. Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker ModelPoster
  917. Let SSMs be ConvNets: State-space Modeling with Optimal Tensor ContractionsSpotlight
  918. Let Your Features Tell The Differences: Understanding Graph Convolution By Feature SplittingPoster
  919. Let the Code LLM Edit Itself When You Edit the CodePoster
  920. LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy AttentionsPoster
  921. Leveraging Driver Field-of-View for Multimodal Ego-Trajectory PredictionPoster
  922. Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGDPoster
  923. Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMsPoster
  924. Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective OptimizationPoster
  925. LiFT: Learning to Fine-Tune via Bayesian Parameter Efficient Meta Fine-TuningSpotlight
  926. Linear Mode Connectivity in Differentiable Tree EnsemblesSpotlight
  927. Linear Multistep Solver Distillation for Fast Sampling of Diffusion ModelsPoster
  928. Linear Partial Gromov-Wasserstein EmbeddingPoster
  929. Linear SCM Identification in the Presence of Confounders and Gaussian NoiseSpotlight
  930. Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical DataSpotlight
  931. Linear combinations of latents in generative models: subspaces and beyondPoster
  932. Lines of Thought in Large Language ModelsPoster
  933. Lipschitz Bandits in Optimal SpacePoster
  934. LiveBench: A Challenging, Contamination-Limited LLM BenchmarkSpotlight
  935. LiveXiv - A Multi-Modal live benchmark based on Arxiv papers contentPoster
  936. LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-TuningPoster
  937. LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model AdaptationPoster
  938. LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA OptimizationOral
  939. LoRA-X: Bridging Foundation Models with Training-Free Cross-Model AdaptationPoster
  940. LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation modelsSpotlight
  941. LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual LearningPoster
  942. Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target PropagationPoster
  943. Local Patterns Generalize Better for Novel AnomaliesPoster
  944. Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic RegressionPoster
  945. Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifoldPoster
  946. Locality Sensitive Avatars From VideoPoster
  947. Locally Connected Echo State Networks for Time Series ForecastingPoster
  948. Logic-Logit: A Logic-Based Approach to Choice ModelingPoster
  949. Long-Context Linear System IdentificationPoster
  950. Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflectionPoster
  951. Long-tailed Adversarial Training with Self-DistillationPoster
  952. LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field EnlargementPoster
  953. Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language ModelsPoster
  954. Looking into User’s Long-term Interests through the Lens of Conservative Evidential LearningPoster
  955. Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network EmbeddingPoster
  956. Lossy Compression with Pretrained Diffusion ModelsPoster
  957. Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution GenerationSpotlight
  958. MA$^2$E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-EncoderPoster
  959. MADGEN: Mass-Spec attends to De Novo Molecular generationPoster
  960. MAESTRO: Masked Encoding Set Transformer with Self-DistillationPoster
  961. MAGNet: Motif-Agnostic Generation of Molecules from ScaffoldsSpotlight
  962. MAI: A Multi-turn Aggregation-Iteration Model for Composed Image RetrievalPoster
  963. MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic ApproximationPoster
  964. MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical SciencePoster
  965. MCNC: Manifold-Constrained Reparameterization for Neural CompressionPoster
  966. MGCFNN: A Neural MultiGrid Solver with Novel Fourier Neural Network for High Wave Number Helmholtz EquationsPoster
  967. MGDA Converges under Generalized Smoothness, ProvablyPoster
  968. MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling RepresentationsPoster
  969. MIND over Body: Adaptive Thinking using Dynamic ComputationOral
  970. MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation ModelsPoster
  971. MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video GenerationPoster
  972. MMEgo: Towards Building Egocentric Multimodal LLMs for Video QAPoster
  973. MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMsPoster
  974. MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual KnowledgePoster
  975. MMSearch: Unveiling the Potential of Large Models as Multi-modal Search EnginesPoster
  976. MOFFlow: Flow Matching for Structure Prediction of Metal-Organic FrameworksPoster
  977. MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane RepresentationPoster
  978. MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable EvaluationsSpotlight
  979. M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory ModelPoster
  980. MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE SolversSpotlight
  981. Machine Unlearning via Simulated Oracle MatchingPoster
  982. Making Transformer Decoders Better Differentiable IndexersPoster
  983. MamBEV: Enabling State Space Models to Learn Birds-Eye-View RepresentationsPoster
  984. MamKO: Mamba-based Koopman operator for modeling and predictive controlSpotlight
  985. Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion SamplingPoster
  986. Mask in the Mirror: Implicit SparsificationPoster
  987. Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMsPoster
  988. Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional VideosPoster
  989. Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight DisentanglementPoster
  990. Matcha: Mitigating Graph Structure Shifts with Test-Time AdaptationPoster
  991. Matérn Kernels for Tunable Implicit Surface ReconstructionPoster
  992. Maximizing the Potential of Synthetic Data: Insights from Random Matrix TheoryPoster
  993. MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification PredictionPoster
  994. Measuring And Improving Engagement of Text-to-Image Generation ModelsPoster
  995. Mechanism and Emergence of Stacked Attention Heads in Multi-Layer TransformersPoster
  996. Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned DatasetsPoster
  997. Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise ClusteringPoster
  998. MeshMask: Physics-Based Simulations with Masked Graph Neural NetworksPoster
  999. Meta-Dynamical State Space Models for Integrative Neural Data AnalysisSpotlight
  1000. Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics SimulationsPoster

ICLR accepted papers in other years

ICLR 2026 (5,356)ICLR 2024 (2,260)ICLR 2023 (1,575)ICLR 2022 (1,094)ICLR 2021 (860)ICLR 2020 (687)ICLR 2019 (502)ICLR 2018 (429)ICLR 2017 (245)

Looking for submission deadlines instead? See the conference deadline calendar.